检索结果-内蒙古大学图书馆

2nd International Conference on Algorithms, High Performance Computing and Artificial Intelligence, AHPCAI 2022

作者： Gao, Jun Huang, Hua Li, Qishen Xia, Shaoqi School of Information Engineering Nanchang Hangkong University Jiangxi Nanchang China School of Software Nanchang Hangkong University Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Jiangxi Nanchang China

ISBN: (纸本)9798350334784

Detecting human key points from a single image is very challenging due to occlusion, blurring, illumination and scale changes. In this paper, this problem is addressed by designing an effective network structure. Since global and local information plays an important role in reasoning about human body structure and invisible keypoints, Multi-level Attention Network (MAN) is proposed. First, compared with traditional multi-resolution networks, it enables multi-resolution feature maps with greater information variance by generating them directly from the highest resolution feature map, which in turn increases the abundance of feature information after final fusion. Secondly, it effectively integrates global and local information in different resolution feature maps through the Feature Alignment Attention Block(FAAB), and intensifies them in a targeted manner. On the COCO dataset, with HRNet (Sun K. et al [1]) as the baseline network, HRNet of inserted MAN improves 1.1-2.3 AP points over the baseline network. © 2022 IEEE.

关键词： attention mechanism Human Pose Estimation keypoint detection

来源：评论

学校读者我要写书评

暂无评论

Research on Monocular Depth Estimation Method based on Multi-Level Attention and Feature Fusion 7

Research on Monocular Depth Estimation Method based on Multi...

引用

7th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Wu, Zhongyu Huang, Hua Li, Qishen Chen, Penghui Nanchang Hangkong University School of Information Engineering Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Jiangxi Nanchang China Nanchang Hangkong University School of Software Jiangxi Nanchang China

ISBN: (纸本)9798350339161

Monocular depth estimation is a fundamental task in computer vision and has drawn increasing attention. Recently, attention-based models and encoder-decoder architectures have led to great improvements in monocular depth estimation. Typically, most of the previous methods used repeated simple up-sampling operations during decoding, which may not make full use of the potential properties of the features extracted by the encoder, and there are problems of inaccurate prediction of the edge and depth maximum region. We propose an attention-based feature fusion module for encoder and decoder. We treat the monocular depth estimation as a pixel-level optimization problem, where the coarsest encoder feature is used to initialize the pixel-level optimization, which is then refined to higher resolution by the proposed attentional feature fusion (AFF). We formulate the prediction problem as ordinal regression over the bin centers that discretize the continuous depth range. It predicts a correspondingly different distribution of bins based on different pictures and we predict bins at the coarsest level using global pooling and MLP layers. In the NYUV2 dataset, the proposed architecture improving original model by 2.5.% and 1.1%, in terms of Log10 and Absolute relative error, respectively. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A method for dynamic infrared image simulation under various natural conditions

A method for dynamic infrared image simulation under various...

引用

MIPPR 2009 - Multispectral image Acquisition and processing: 6th International Symposium on Multispectral image processing and pattern recognition

作者： Zheng, Lulu Sun, Siyuan Zhang, Tianxu Li, Ziliang Wan, Meijun State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478054

Infrared image simulation plays an important role in many fields. This paper presents a method for dynamic infrared image simulation under various natural conditions. Firstly, we analyze the infrared imaging rationale, considering various affected factors of temperature, radiance filed and atmospheric attenuation based on the heat transfer equation. Secondly, we present a reasonable simulation procedure based on the Vega Application Interface (API). Especially, a hybrid simulation idea is put forward and an improved strategy for different objects is carried out. The performance of this approach is evaluated by simulating two kinds of targets. Results show that the method proposed is valid compared with the real images under the same condition. In addition, this approach has relatively low calculation complexity but high fidelity, and satisfies the requirement of real time. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

CDE-Net: A semi-supervised nucleus instance segmentation method based on center deviation estimation 22

CDE-Net: A semi-supervised nucleus instance segmentation met...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Yan, Yi Wang, Da-Han Ye, Haili Zhu, Shunzhi Li, Jianmin School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China

ISBN: (纸本)9781450396110

Cell nucleus segmentation is an important step in the diagnosis of tumor malignancy. In the case of out-of-focus, the cell nucleus boundary tends to be blurred, which increases the difficulty of cell segmentation and marking. Therefore, in the case of marking only some core instances, it is very important to realize the segmentation of core instances. In this paper, we propose a semi-supervised nucleus instance segmentation method based on anchor bias prediction that is achieved by our proposed center deviation estimation network (CDE-Net). By introducing the CDE branch to predict the offset degree of the anchor frame, and weighting the confidence of the anchor frame, more accurate prediction results can be obtained. The model adopts the semi-supervised training method to progressively learn the CDE-Net model, which alleviates the problem of imbalance between positive and negative samples caused by only marking part of the nuclear samples. The experimental results show that CDE-Net is superior to Mask R-CNN in many evaluation indicators, and achieves SOTA on the partially labelled MoNuSeg data set. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Gravel image Segmentation in Noisy Background Based on Partial Entropy Method

引用

中国地质大学学报(英文版) 2000年第1期11卷 92-94页

作者： Wang Guangjun Tian Jinwen Chen Zhenyu Liu Jian Wu Guoping State Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology WuHan 430074 Faculty of Information Engineering China University of Geosciences Wuhan 430074

Because of wide variation in gray levels and particle dimensions and the presence of many small gravel objects in the background, as well as corrupting the image by noise, it is difficult o segment gravel objects. In this paper, we develop a partial entropy method and succeed to realize gravel objects segmentation. We give entropy principles and fur calculation methods. Moreover, we use minimum entropy error automaticly to select a threshold to segment image. We introduce the filter method using mathematical morphology. The segment experiments are performed by using different window dimensions for a group of gravel image and demonstrates that this method has high segmentation rate and low noise sensitivity.

关键词： partial entropy segmentation mathematical morphology gravel threshold filter

来源：评论

学校读者我要写书评

暂无评论

Detection of billet character in complex production line scene

Detection of billet character in complex production line sce...

引用

2012 3rd International Conference on Digital Manufacturing and Automation, ICDMA 2012

作者： Hong, Hanyu Yu, Zhejun Zhang, Xiuhua Laboratory for Image Processing and Intelligent Control Wuhan Institute of Technology Wuhan 430205 China Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780769547725

Character information is hard to detect in billet scene images by CCD camera. In this paper, we present a method for detection of billet characters from measurements of recursive segmented image. This recursive segmented method can be used in a wide variety of billet scenes. According to high temperature and complex scene in the rolling line, we use an effective clustering and projection characteristics to determine the terminal condition of recursive segmentation. Then we can label character candidate regions in turn by this effective characteristics, and select the regions we want to achieve. The experiments show that this method makes full use of the characteristics of region and clustering. It can improve the quality of detection, and the detection result meets the need of practical application. © 2012 IEEE.

关键词： CCD cameras

来源：评论

学校读者我要写书评

暂无评论

Handwritten mathematical expression recognition with self-attention 4

Handwritten mathematical expression recognition with self-at...

引用

4th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2021

作者： Chi, Xueke Wang, Da-Han Wu, Yuefeng Wu, Yun Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China

ISBN: (纸本)9781450385053

Attention-based encoder-decoder models have made great success on handwritten mathematical expression recognition in recent years. However, this kind of method has the problem of attention drift, because under the local attention mechanism based on RNN, the high similarity between coding features can cause attention confusion. To settle this problem, we propose an encoder-decoder model with self-attention, which captures the global information of the feature map and fuses the local information of the CNN as complementary features. Experiments are conducted on the CROHME2014 and CROHME 2016 competition datasets. The experimental results show that, when only using the official training dataset, the proposed method achieves recognition accuracies of 51.98% and 50.74% on the CROHME2014 and CROHME2016 competition datasets, respectively, which outperforms the other methods significantly. The improvements demonstrate the effectiveness of the self-attention module. © 2021 ACM.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Dynamic Updating of Partial Feature Maps for image-based Real-Time recognition of Online Handwritten Chinese Text 22

Dynamic Updating of Partial Feature Maps for Image-based Rea...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Wu, Yuefeng Zhong, Ying Wang, Da-Han Chi, Xueke School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China

ISBN: (纸本)9781450396110

Online handwritten Chinese text recognition (OHCTR) has made certain progress in recent years. Most methods currently used are image-based text recognition which has achieved some success. However, it should be noticed that, it is difficult to smoothly recognize online handwritten texts in real-time, especially for long text lines. For real-time recognition of OHCT, the feature extraction of ever-extending text lines will be time-consuming and make the system un-humanization. Moreover, the feature extraction of the non-written part will be performed repeatedly, which is not suitable and has not been addressed by previous works. In this paper, we propose a method to dynamically update partial feature maps of the newly written part for real-time OHCTR. The basic idea is to update the feature maps according to the newly written stroke, which can avoid repeated convolutional computations and thus improve the recognition speed. The proposed method can handle the case of delayed strokes, and can greatly improve the speed of real-time recognition without any loss of accuracy. Experiments on the CASIA-OLHWDB and the ICDAR-2013 competition database demonstrate that our real-time recognition speed are multiplier increased compared with traditional text line recognition methods. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Attention-based Deep Learning Methods for Document Layout Analysis 22

Attention-based Deep Learning Methods for Document Layout An...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Sun, Hao-Yue Zhong, Ying Wang, Da-Han School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China

ISBN: (纸本)9781450396110

Deep learning has unique advantages in document layout analysis. In this paper, we propose to use the attention mechanism to improve the deep learning based methods for document layout analysis, and conducted comprehensive experiments to evaluate the effects of different models/modules/backbones. Firstly, the evaluated backbones include ResNet-50 and ResNet-101 for their high performance, and the popularly used Fast RCNN and Faster RCNN based methods. Secondly, for the loss function, the Focal loss function is also adopted to improve the performance of document layout analysis. Most importantly, we propose to integrate the attention mechanism into the deep learning-based methods to improve the performance. Specifically, when calculating the residual using this ResNet network, we use the attention to perform a dot product operation on the degraded accuracy to correct the residual error of the network calculation, which obtains a higher detection accuracy. We conducted experiments on the PubLayNet, DocBank and ICDAR-2013 datasets for evaluation. Experimental results show that, with the attention mechanism, the basic deep learning-based methods has been significantly improved in the task of document layout analysis, demonstrating the effectiveness of the proposed method. The focal loss that is designed to overcome the problem of imbalance number of training samples is also effective for document layout analysis. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

High precision discrete wavelet transform based on moment and systolic implementation

High precision discrete wavelet transform based on moment an...

引用

MIPPR 2009 - Medical Imaging, Parallel processing of images, and Optimization Techniques: 6th International Symposium on Multispectral image processing and pattern recognition

作者： Liu, Zhenbing Liu, Jianguo Wang, Guoyou State Key Laboratory for Multispectral Information Processing Technologies Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan HB 430074 China

ISBN: (纸本)9780819478085

Discrete wavelet transform (DWT) is an important tool in digital signal processing. In this paper, a new algorithm to compute DWT is proposed: first, based on the previous work of performing discrete Fourier transform (DFT) via linear sums of discrete moments, we introduce a multiplierless DFT by performing appropriate bit operations and shift operations in binary system;then by convolution theorem, the computation is transformed to the computation of DFT. In addition, a efficient systolic array is designed to implement the DWT which is a demonstration of the locality of dataflow in the algorithms. The approach is also applicable to multi-dimensional DWT. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Discrete Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：